EP3386215A1 - Hearing aid and method for operating a hearing aid - Google Patents
Hearing aid and method for operating a hearing aid Download PDFInfo
- Publication number
- EP3386215A1 EP3386215A1 EP18157220.7A EP18157220A EP3386215A1 EP 3386215 A1 EP3386215 A1 EP 3386215A1 EP 18157220 A EP18157220 A EP 18157220A EP 3386215 A1 EP3386215 A1 EP 3386215A1
- Authority
- EP
- European Patent Office
- Prior art keywords
- signal
- classifiers
- signal processing
- acoustic
- hearing
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 51
- 238000012545 processing Methods 0.000 claims abstract description 58
- 238000011156 evaluation Methods 0.000 claims description 11
- 230000006641 stabilisation Effects 0.000 claims description 8
- 238000011105 stabilization Methods 0.000 claims description 8
- 230000003595 spectral effect Effects 0.000 claims description 6
- 230000008859 change Effects 0.000 claims description 5
- 230000000694 effects Effects 0.000 claims description 4
- 230000005484 gravity Effects 0.000 claims description 4
- 230000002123 temporal effect Effects 0.000 claims description 3
- 230000008569 process Effects 0.000 abstract description 3
- 230000006978 adaptation Effects 0.000 description 7
- 230000006870 function Effects 0.000 description 7
- 238000001514 detection method Methods 0.000 description 6
- MOVRNJGDXREIBM-UHFFFAOYSA-N aid-1 Chemical compound O=C1NC(=O)C(C)=CN1C1OC(COP(O)(=O)OC2C(OC(C2)N2C3=C(C(NC(N)=N3)=O)N=C2)COP(O)(=O)OC2C(OC(C2)N2C3=C(C(NC(N)=N3)=O)N=C2)COP(O)(=O)OC2C(OC(C2)N2C3=C(C(NC(N)=N3)=O)N=C2)COP(O)(=O)OC2C(OC(C2)N2C(NC(=O)C(C)=C2)=O)COP(O)(=O)OC2C(OC(C2)N2C3=C(C(NC(N)=N3)=O)N=C2)COP(O)(=O)OC2C(OC(C2)N2C3=C(C(NC(N)=N3)=O)N=C2)COP(O)(=O)OC2C(OC(C2)N2C3=C(C(NC(N)=N3)=O)N=C2)COP(O)(=O)OC2C(OC(C2)N2C(NC(=O)C(C)=C2)=O)COP(O)(=O)OC2C(OC(C2)N2C3=C(C(NC(N)=N3)=O)N=C2)COP(O)(=O)OC2C(OC(C2)N2C3=C(C(NC(N)=N3)=O)N=C2)COP(O)(=O)OC2C(OC(C2)N2C3=C(C(NC(N)=N3)=O)N=C2)COP(O)(=O)OC2C(OC(C2)N2C(NC(=O)C(C)=C2)=O)COP(O)(=O)OC2C(OC(C2)N2C3=C(C(NC(N)=N3)=O)N=C2)COP(O)(=O)OC2C(OC(C2)N2C3=C(C(NC(N)=N3)=O)N=C2)COP(O)(=O)OC2C(OC(C2)N2C3=C(C(NC(N)=N3)=O)N=C2)CO)C(O)C1 MOVRNJGDXREIBM-UHFFFAOYSA-N 0.000 description 5
- 230000004927 fusion Effects 0.000 description 5
- 238000011161 development Methods 0.000 description 4
- 230000018109 developmental process Effects 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000003203 everyday effect Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000005236 sound signal Effects 0.000 description 2
- 208000009205 Tinnitus Diseases 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 230000003416 augmentation Effects 0.000 description 1
- 210000000988 bone and bone Anatomy 0.000 description 1
- 230000008094 contradictory effect Effects 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 239000007943 implant Substances 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012913 prioritisation Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000008054 signal transmission Effects 0.000 description 1
- 231100000886 tinnitus Toxicity 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
- H04R25/00—Deaf-aid sets, i.e. electro-acoustic or electro-mechanical hearing aids; Electric tinnitus maskers providing an auditory perception
- H04R25/50—Customised settings for obtaining desired overall acoustical characteristics
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
- H04R25/00—Deaf-aid sets, i.e. electro-acoustic or electro-mechanical hearing aids; Electric tinnitus maskers providing an auditory perception
- H04R25/50—Customised settings for obtaining desired overall acoustical characteristics
- H04R25/505—Customised settings for obtaining desired overall acoustical characteristics using digital signal processing
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L21/00—Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
- G10L21/02—Speech enhancement, e.g. noise reduction or echo cancellation
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/78—Detection of presence or absence of voice signals
- G10L25/81—Detection of presence or absence of voice signals for discriminating voice from music
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/78—Detection of presence or absence of voice signals
- G10L25/84—Detection of presence or absence of voice signals for discriminating voice from noise
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
- H04R25/00—Deaf-aid sets, i.e. electro-acoustic or electro-mechanical hearing aids; Electric tinnitus maskers providing an auditory perception
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
- H04R25/00—Deaf-aid sets, i.e. electro-acoustic or electro-mechanical hearing aids; Electric tinnitus maskers providing an auditory perception
- H04R25/43—Electronic input selection or mixing based on input signal analysis, e.g. mixing or selection between microphone and telecoil or between microphones with different directivity characteristics
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
- H04R25/00—Deaf-aid sets, i.e. electro-acoustic or electro-mechanical hearing aids; Electric tinnitus maskers providing an auditory perception
- H04R25/50—Customised settings for obtaining desired overall acoustical characteristics
- H04R25/505—Customised settings for obtaining desired overall acoustical characteristics using digital signal processing
- H04R25/507—Customised settings for obtaining desired overall acoustical characteristics using digital signal processing implemented by neural network or fuzzy logic
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
- H04R25/00—Deaf-aid sets, i.e. electro-acoustic or electro-mechanical hearing aids; Electric tinnitus maskers providing an auditory perception
- H04R25/70—Adaptation of deaf aid to hearing loss, e.g. initial electronic fitting
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
- H04R3/00—Circuits for transducers, loudspeakers or microphones
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
- H04R2225/00—Details of deaf aids covered by H04R25/00, not provided for in any of its subgroups
- H04R2225/39—Aspects relating to automatic logging of sound environment parameters and the performance of the hearing aid during use, e.g. histogram logging, or of user selected programs or settings in the hearing aid, e.g. usage logging
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
- H04R2225/00—Details of deaf aids covered by H04R25/00, not provided for in any of its subgroups
- H04R2225/41—Detection or adaptation of hearing aid parameters or programs to listening situation, e.g. pub, forest
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
- H04R2225/00—Details of deaf aids covered by H04R25/00, not provided for in any of its subgroups
- H04R2225/43—Signal processing in hearing aids to enhance the speech intelligibility
Definitions
- the invention relates to a method for operating a hearing device and to a hearing device which is set up in particular for carrying out the method.
- Hearing devices are usually used to output a sound signal to the hearing of the wearer of this hearing.
- the output is effected by means of an output transducer, usually acoustically via airborne sound by means of a loudspeaker (also referred to as “receiver” or “receiver”).
- a loudspeaker also referred to as “receiver” or “receiver”
- hearing aid devices also short: hearing aids
- the hearing devices normally comprise an acoustic input transducer (in particular a microphone) and a signal processor which is adapted to process the input signal (also: microphone signal) generated by the input transducer from the ambient sound using at least one custom-deposited signal processing algorithm such that a Hearing reduction of the wearer of the hearing device is at least partially compensated.
- the output transducer can also be, in addition to a loudspeaker, alternatively a so-called bone conduction earpiece or a cochlear implant, which are set up for the mechanical or electrical coupling of the sound signal into the hearing of the wearer.
- devices such as, for example, so-called tinnitus maskers, headsets, headphones and the like also fall in particular under the term hearing devices.
- Modern hearing devices in particular hearing aids, often comprise a so-called classifier, which is usually designed as part of the signal processor which executes the respective signal processing algorithm or algorithms.
- a classifier is again usually an algorithm that serves to conclude an existing listening situation based on the ambient sound detected by means of the microphone.
- an adaptation of the or the respective signal processing algorithm to the characteristic properties of the present auditory situation is then usually carried out.
- the hearing device is thereby intended to pass on the information relevant for the user to the hearing situation. For example, for the clearest possible output of music, different settings (parameter values of different parameters) of the one or more of the signal processing algorithms are required than for intelligible speech output with loud ambient noise.
- the correspondingly assigned parameters are then changed.
- Usual Hörsituationen are z. Eg speech at rest, speech at background noise, music listening, (driving in) vehicle.
- various features are first derived from the microphone signal (or an input signal formed therefrom). These features are fed to the classifier, which is analyzed using analysis models such.
- analysis models such as a so-called “Gaussian-mixed-mode analysis”, a “Hidden Markov model”, a neural network or the like probabilities for the presence of certain auditory situations outputs.
- a classifier is "trained" by means of databases in which a large number of different representative auditory samples are stored for the respective listening situations, to the respective hearing situation.
- the disadvantage of this is that not all possibly occurring in everyday life combinations of sounds can be mapped in such a database usually. Thus, it may already come to misclassification of some Hörsituationen already.
- the invention has for its object to provide an improved hearing.
- the method according to the invention serves to operate a hearing device which comprises at least one microphone for converting ambient sound into a microphone signal.
- a number of features also referred to as “features”
- At least three classifiers which are implemented independently for the analysis of one (preferably fixed) associated acoustic dimension, are each supplied with a specifically assigned selection from these characteristics.
- information about an expression of the acoustic dimension assigned to this classifier is subsequently generated in each case.
- at least one signal processing algorithm which is processed (ie executed) for processing the microphone signal or the input signal is then modified.
- a change in the signal processing algorithm is understood here and below as meaning in particular that at least one parameter contained in the signal processing algorithm is set to another parameter value as a function of the expression of the acoustic dimension or at least one of the acoustic dimensions.
- another setting of the signal processing algorithm is "approached” (ie, effected or made).
- acoustic dimension is understood here and below to mean, in particular, a group of listening situations which are related on the basis of their specific properties.
- the listening situations depicted in such an acoustic dimension are each described by the same features (features) and in this case differ, in particular, on the basis of the current value of the respective features.
- the term "expression" of the respective acoustic dimension is understood here and below in particular as meaning (in the sense of a binary distinction) or (in a preferred variant) to what degree (for example to what percentage) the respective one or more in the respective acoustic dimension shown hearing situation is present.
- a degree or percentage preferably represents a probability value for the presence of the respective hearing situation.
- the listening situations “speech at rest”, “speech in noise” or (especially only) "Noise” (ie, there is no language) be mapped, the information about the expression preferably again in each case percentages include (eg 30% probability of speech in noise and 70% probability of only noise).
- the hearing device comprises, as described above, at least one microphone for converting the ambient sound into the microphone signal and a signal processor in which at least the three classifiers described above are implemented independently of one another for the analysis of the respective (preferably fixed) associated acoustic dimension.
- the signal processor is set up to perform the inventive method preferably automatically.
- the signal processor is set up to derive the number of features from the microphone signal or the input signal formed therefrom, to supply each of the three classifiers with a specifically assigned selection from the features, with the aid of the respective classifier information about the characteristics of the respective associated ones To generate acoustic dimension and depending on at least one of the three information at least one (preferably corresponding to the acoustic dimension assigned) signal processing algorithm to change and preferably apply to the microphone signal or the input signal.
- the signal processor (also referred to as signal processing unit) is formed at least in the core by a microcontroller with a processor and a data memory in which the functionality for performing the method according to the invention in the form of operating software ("firmware") is implemented by programming, so that the method - optionally in interaction with a user of the hearing device - is automatically performed in the execution of the operating software in the microcontroller.
- the signal processor is constituted by a non-programmable electronic component, e.g. an ASIC, in which the functionality for carrying out the method according to the invention is implemented by means of circuitry.
- At least three classifiers are set up and provided for analysis in each case of an assigned acoustic dimension and thus in particular for the detection of a respective hearing situation, it is advantageously made possible that at least three hearing situations can be recognized independently of each other. As a result, the flexibility of the hearing device in detecting hearing situations is advantageously increased.
- the invention is based on the recognition that at least some listening situations may also be completely independent of one another (ie in particular not influencing each other or only to a negligible extent) from one another and parallel to one another.
- the risk can be reduced that mutually exclusive and, in particular, contradictory classifications (ie assessment of the currently present acoustic situation) occur, at least with regard to the at least three acoustic dimensions analyzed by the respective assigned classifier.
- contradictory classifications ie assessment of the currently present acoustic situation
- simple can Ways completelyly present in parallel present hearing situations and be taken into account in the change of the signal processing algorithm.
- the hearing device according to the invention has the same advantages as the method according to the invention for operating the hearing device.
- the signal processing algorithms preferably "work" on (at least) one respective associated acoustic dimension, ie. H. the signal processing algorithms are used to process (eg filtering, amplifying, attenuating) signal components that are relevant to the listening situations contained or reproduced in the respectively assigned acoustic dimension.
- the signal processing algorithms comprise at least one, preferably a plurality of parameters which can be changed in their parameter values.
- the parameter values can also be changed in several gradations (gradual or continuous) depending on the respective probability of the characteristic. This allows a particularly flexible and advantageously to a variety of gradual differences between multiple listening situations customizable signal processing.
- At least two of the at least three classifiers are each supplied with a different selection from the characteristics. This is understood here and below as meaning in particular that a different number and / or different features are selected and supplied to the respective classifier.
- each of the classifiers with the correspondingly assigned selection is supplied with features relevant only to the analysis of the assigned acoustic dimension.
- features relevant only to the analysis of the assigned acoustic dimension preferably only those features are selected and supplied which are actually required for determining the auditory situation depicted in the respective acoustic dimension.
- a specific analysis algorithm for evaluating the (respectively specific) supplied features is used for each of the classifiers.
- This can advantageously also save computational effort.
- comparatively complicated algorithms or analysis models such. As Gaussian mixed modes, neural networks or hidden Markov models, which are used in particular for the analysis of a variety of different, independent characteristics eliminated.
- each of the classifiers is thus “tailored” (ie adapted or designed) to a concrete "problem", ie with regard to its analysis algorithm, to the acoustic dimension concretely assigned to this classifier.
- the comparatively complex analysis models described above can nevertheless be used for specific acoustic dimensions in the context of the invention, whereby in this case, due to the orientation of the corresponding classifier to one or a few auditory situations encompassed by the specific acoustic dimension, effort is required to implement such a comparatively complex model can be saved.
- the dimensions "vehicle”, “music” and “language” are used as the at least three acoustic dimensions.
- These three acoustic dimensions are, in particular, the dimensions that usually occur particularly frequently in the everyday life of a user of the hearing device and are also independent of each other.
- a fourth classifier is used to analyze a fourth acoustic dimension, which is in particular the loudness (also: “loudness”) of ambient noise (also referred to as “noise”).
- the characteristics of this acoustic dimension preferably extend gradually or continuously over a plurality of intermediate stages from very quiet to very loud.
- the information on the characteristics, in particular of the acoustic dimensions vehicle and music can optionally be “binary", i. H. it is only recognized whether driving in the vehicle is present or not, or whether music is heard or not.
- all the information of the other three acoustic dimensions is present as a kind of probability value continuously. This is particularly advantageous because errors in the analysis of the respective acoustic dimension can not be excluded, and as a result, in contrast to binary information, "softer" transitions between different settings can be effected in a simple manner.
- features are derived from the microphone signal or the input signal which originate from a (in particular non-terminating)
- signal level 4 Hz envelope modulation, onset content, background noise level (also referred to as noise floor level, optionally at a given frequency), spectral centroid of the background noise, stationarity (in particular at a given frequency), tonality and wind activity.
- background noise level also referred to as noise floor level, optionally at a given frequency
- spectral centroid of the background noise also referred to as stationarity (in particular at a given frequency)
- tonality tonality
- the acoustic dimension vehicle is assigned at least the characteristics level of the background noise, spectral center of gravity of the background noise and stationarity (and optionally also the characteristic of the wind activity).
- the acoustic dimension music is preferably assigned the characteristics onset content, tonality and level of the background noise.
- the characteristics of onset content and 4 Hz envelope modulation are assigned to the acoustic dimension speech.
- the possibly existing dimension loudness of the ambient noise is assigned in particular the characteristics level of the background noise, signal level and spectral center of gravity of the background noise.
- a specifically assigned temporal stabilization is taken into account for each classifier.
- this condition the expression
- a moving average is formed over (in particular a predefined number of) preceding time segments.
- a type of "dead-time element” by means of which the probability is increased in a subsequent period of time that the characteristic present in the preceding time period is still present. For example, assuming that driving in the vehicle has been detected in the previous five minutes, it is assumed that this situation is still present.
- vehicle and music are comparatively "strong" stabilizations are used, ie only comparatively slow or rare changes in the correspondingly assigned listening situations are assumed.
- no or only a "weak” stabilization is undertaken, since here rapid and / or frequent changes of the listening situations are assumed.
- Voice situations can often last only a few seconds (for example about 5 seconds) or a few minutes, whereas driving in the vehicle usually lasts for several minutes (for example more than 3 to 30 minutes or even hours).
- a further optional variant for stabilization can also take place via a counting principle in which a counter (“counter”) is incremented at a comparatively fast (for example 100 milliseconds to a few seconds) detection cycle and only when a limit value for this counter is exceeded the "Detection "of the respective hearing situation is triggered. This is expedient, for example, as short-term stabilization in the case of a common classifier for "all" listening situations.
- the respective signal processing algorithm is adapted as a function of at least two of the at least three information about the expression of the respective associated acoustic dimension. In at least one signal processing algorithm, therefore, the information of several classifiers is taken into account.
- the respective information of the individual classifiers is in particular first supplied to a fusion member for a common evaluation ("merged"). On the basis of this joint evaluation of all information in particular a total information about the present hearing situations is created.
- a dominant hearing situation is preferably determined - in particular on the basis of the degree of expressiveness representing the probability.
- the or the respective signal processing algorithm is adapted to this dominant listening situation.
- a prioritization of a hearing situation takes place in that the or the respective signal processing algorithm is changed only as a function of the dominant hearing situation, while other signal processing algorithms and / or the parameters dependent on other hearing situations remain unchanged or a parameter value which does not Has an influence on the signal processing.
- a hearing situation designated as a sub-situation is determined, which has a lower dominance than the dominant hearing situation.
- This or the respective sub-situation is additionally taken into account in the above-mentioned adaptation of the or the respective signal processing algorithm to the dominant hearing situation and / or adaptation of a signal processing algorithm specifically assigned to the acoustic dimension of this sub-situation.
- this sub-situation leads to a smaller change of the respectively assigned parameter compared to the dominant hearing situation.
- a signal processing algorithm serving as clear as possible in the case of noise is then comparatively strongly modified in one or more parameters in order to achieve as high a speech intelligibility as possible.
- parameters that attenuate ambient noise are set less (as if there is only a noise) so as not to completely dampen the sounds of the music.
- a (especially additional) signal processing algorithm for clear sound reproduction of music is set less strongly than in music as the dominant listening situation (but stronger than in any music) in order not to mask the speech components.
- the parallel existence of a plurality of hearing situations is preferably taken into account in at least one of the possibly multiple signal processing algorithms.
- each signal processing algorithm is assigned to at least one of the classifiers.
- at least one parameter of each signal processing algorithm is changed as a function of the information output by the respective classifier about the characteristic of the assigned acoustic dimension.
- this parameter or its parameter value is designed as a function of the respective information.
- the information about the expression of the respective acoustic dimension is used in particular directly for an adaptation of the signal processing.
- each classifier "controls" at least one parameter of at least one signal processing algorithm. A common evaluation of all information can be omitted here.
- state information is fed to at least one of the classifiers and is generated independently of the microphone signal or the input signal.
- This state information is taken into account in particular in addition to the evaluation of the respective acoustic dimension.
- this is a movement and / or location information, for example, for the evaluation of the acoustic Dimension vehicle is used.
- This movement and / or location information is generated, for example, with an acceleration or (global) position sensor arranged in the hearing device itself or in a signal transmission technology connected to it (eg, a smartphone).
- the probability of the presence of the hearing situation driving in the vehicle can be increased in a simple manner in addition to the acoustic evaluation on the basis of a present (having a predetermined value) movement speed in the evaluation of the acoustic dimension vehicle. This is also called "augmentation" of a classifier.
- FIG. 1 is a hearing aid, a hearing aid, briefly referred to as "hearing aid 1" shown.
- the hearing aid 1 comprises as electrical components which are housed in a housing 2, two microphones 3, a signal processor 4 and a speaker 5.
- the hearing aid 1 also comprises a battery 6, alternatively as a primary cell (for example, a button cell ) or as a secondary cell (ie as a rechargeable battery) may be configured.
- a primary cell for example, a button cell
- a secondary cell ie as a rechargeable battery
- These two microphone signals S M are fed to the signal processor 4, which, executing four signal processing algorithms A 1 , A 2 , A 3 and A 4 from these microphone signals S M generates an output signal S A and this to a speaker 5, which is an output transducer, outputs.
- the loudspeaker 5 converts the output signal S A into airborne sound, which is transmitted to the hearing of a user or wearer (in short: hearing aid wearer) of the hearing aid via a sound tube 7 connected to the housing 2 and an earpiece 8 connected therewith (in the intended wearing state of the hearing aid 1) 1 is output.
- the hearing aid 1, specifically its signal processor 4 is set up, in the following with reference to FIG FIG. 2 and FIG. 3 to perform the procedure described in more detail automatically.
- the hearing device 1, specifically its signal processor 4 comprises at least three classifiers K S , K M and K F. These three classifiers K S , K M and K F are each set up and configured to analyze a specifically assigned acoustic dimension.
- the classifier K S is concretely designed to evaluate the acoustic dimension "language", ie whether speech, speech in the noise or only a noise is present.
- the classifier K M is specifically designed to evaluate the acoustic dimension "music", ie whether ambient sound is dominated by music.
- the classifier K F is specifically designed to evaluate the acoustic dimension "vehicle”, ie to determine whether the hearing aid wearer is driving in a vehicle.
- the signal processor 4 further comprises a feature analysis module 10 (also referred to as “feature extraction module”) which is adapted to generate a number of (signal) signals from the microphone signals S M , specifically from an input signal S E formed from these microphone signals S M. Derive characteristics.
- the classifiers K S , K M and K F are each supplied with a different and specifically assigned selection from these characteristics.
- the respective classifier K S , K M or K F determines an expression of the respective associated acoustic dimension, ie to what degree one of the acoustic dimension specifically assigned hearing situation exists, and outputs this expression as respective information.
- a first method step 20 the microphone signals S M generated from the detected ambient sound and combined by the signal processor 4 to the input signal S E (specifically mixed to a directional microphone signal).
- the input signal S E formed from the microphone signals S M is supplied to the feature analysis module 10 and the number of features is derived therefrom.
- the specific characteristics are the background noise level (characteristic "M P "), the spectral center of gravity of the background noise ("M Z “ feature), the stationarity of the signal (“M M “ feature), a wind activity (Feature “M W “), an onset content of the signal (feature “M O “), a tonality (feature “M T “), and a 4 Hertz envelope modulation (feature “M E “).
- the classifier K S is supplied with the features M E and M O for the purpose of analyzing the acoustic dimension speech.
- the classifier K M is supplied with the characteristics M O , M T and Mp for analysis of the acoustic dimension of music.
- the classifier K F is supplied with the characteristics M P , M W , M Z and M M for analyzing the acoustic dimension driving in the vehicle.
- the classifiers K S , K M and K F then determine on the basis of the respectively supplied characteristics by means of specifically adapted analysis algorithms to what extent, ie to what degree the respective acoustic dimension is pronounced.
- the classifier K S is used to determine with which probability speech is at rest, speech in noise or only a noise.
- the classifier K M is determined accordingly, with what probability music exists.
- the classifier K F is determined with what probability the hearing aid wearer drives in a vehicle or not.
- only "binary" is determined whether speech, possibly in noise or only noise, or whether music or driving in the vehicle is present or not.
- the respective expression of the acoustic dimensions is output in a method step 50 to a fusion module 60 (see FIG. 2 ) by bringing together the respective information and comparing it with each other.
- a decision is made in the fusion module 60 as to which dimension, specifically which hearing situation depicted therein, is currently to be regarded as dominant and which listening situations are currently of secondary importance or can be completely excluded.
- a number of the parameters relevant to the dominant and the less relevant hearing situations are changed by the fusion module in a number of the stored signal processing algorithms A 1 to A 4 , so that the signal processing is adapted primarily to the dominant hearing situation and slightly to the less relevant hearing situation.
- Each of the signal processing algorithms A 1 to A 4 is in each case adapted to the presence of a hearing situation, possibly also parallel to other listening situations.
- the classifier K F includes in a manner not shown a temporal stabilization. This is particularly geared to the fact that a ride in the vehicle usually lasts longer time, and thus in the event that already in previous periods of, for example, each 30 seconds to five minutes duration, driving in the vehicle was detected and assuming that the situation driving in the vehicle still lasts the probability for the existence of this hearing situation is already increased in advance. The same is also set up and provided in the classifier K M.
- At least one of the signal processing algorithms A 1 , A 2 , A 3 and A 4 is assigned to each of the classifiers K S , K M and K F such that a plurality of signal processing algorithms A 1 , A 2 , A 3 and A 4 parameters are designed to be changeable as a function of the characteristics of the respective acoustic dimension.
- a plurality of signal processing algorithms A 1 , A 2 , A 3 and A 4 parameters are designed to be changeable as a function of the characteristics of the respective acoustic dimension.
- the signal processing algorithm A 1 depends only on the information of the classifier K S.
- the information of all classifiers K S , K M and K F flows into the signal processing algorithm A 3 , where they lead to the modification of several parameters.
- the object of the invention is not limited to the embodiments described above. Rather, other embodiments of the invention may be derived by those skilled in the art from the foregoing description.
- the individual features of the invention described with reference to the various exemplary embodiments and their design variants can also be combined with one another in a different manner.
- the hearing device 1 instead of the illustrated behind-the-ear hearing device, the hearing device 1 may also be designed as an in-the-ear hearing device.
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Neurosurgery (AREA)
- Otolaryngology (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Automation & Control Theory (AREA)
- Evolutionary Computation (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Quality & Reliability (AREA)
- Circuit For Audible Band Transducer (AREA)
- Soundproofing, Sound Blocking, And Sound Damping (AREA)
Abstract
Bei einem erfindungsgemäßen Verfahren zum Betrieb einer Hörvorrichtung (1), die wenigstens ein Mikrophon (3) zur Wandlung von Umgebungsschall in ein Mikrophonsignal (S M ) umfasst, wird aus dem Mikrophonsignal (S M ) oder einem daraus gebildeten Eingangssignal (S E ) eine Anzahl von Merkmalen (M E , M O , M T , M P , M W , M Z , M M ) abgeleitet. Wenigstens drei Klassifikatoren (K S , K M , K F ), die unabhängig voneinander zur Analyse jeweils einer zugeordneten akustischen Dimension implementiert sind, wird jeweils eine spezifisch zugeordnete Auswahl aus diesen Merkmalen (M E , M O , M T , M P , M W , M Z , M M ) zugeführt. Mittels des jeweiligen Klassifikators (K S , K M , K F ) wird jeweils eine Information über eine Ausprägung der diesem Klassifikator (K S , K M , K F ) zugeordneten akustischen Dimension generiert. In Abhängigkeit von mindestens einer der wenigstens drei Informationen über die jeweilige Ausprägung der zugeordneten akustischen Dimension wird daraufhin wenigstens ein Signalverarbeitungsalgorithmus (A 1 , A 2 , A 3 , A 4 ), der zur Verarbeitung des Mikrophonsignals (S M ) oder des Eingangssignals (S E ) in ein Ausgangssignal (S A ) abgearbeitet wird, verändert.In a method according to the invention for operating a hearing device (1) which comprises at least one microphone (3) for converting ambient sound into a microphone signal (SM), the microphone signal (SM) or an input signal (SE) formed therefrom becomes a number of features (ME, MO, MT, MP, MW, MZ, MM) derived. At least three classifiers (K S, K M, K F), which are implemented independently of each other for analysis of an associated acoustic dimension, are each supplied with a specifically assigned selection of these characteristics (M E, M O, M T, M P, M W, M Z, M M). By means of the respective classifier (K S, K M, K F), in each case information is generated about an expression of the acoustic dimension assigned to this classifier (K S, K M, K F). Depending on at least one of the at least three information about the respective expression of the associated acoustic dimension, at least one signal processing algorithm (A 1, A 2, A 3, A 4), which is used to process the microphone signal (SM) or the input signal (SE), in an output signal (SA) is processed, changed.
Description
Die Erfindung betrifft ein Verfahren zum Betrieb einer Hörvorrichtung sowie eine Hörvorrichtung, die insbesondere zur Durchführung des Verfahrens eingerichtet ist.The invention relates to a method for operating a hearing device and to a hearing device which is set up in particular for carrying out the method.
Hörvorrichtungen dienen üblicherweise zur Ausgabe eines Tonsignals an das Gehör des Trägers dieser Hörvorrichtung. Die Ausgabe erfolgt dabei mittels eines Ausgabewandlers, meist auf akustischem Weg über Luftschall mittels eines Lautsprechers (auch als "Hörer" oder "Receiver" bezeichnet). Häufig kommen derartige Hörvorrichtungen dabei als sogenannte Hörhilfegeräte (auch kurz: Hörgeräte) zum Einsatz. Dazu umfassen die Hörvorrichtungen normalerweise einen akustischen Eingangswandler (insbesondere ein Mikrophon) und einen Signalprozessor, der dazu eingerichtet ist, das von dem Eingangswandler aus dem Umgebungsschall erzeugte Eingangssignal (auch: Mikrophonsignal) unter Anwendung mindestens eines üblicherweise nutzerspezifisch hinterlegten Signalverarbeitungsalgorithmus derart zu verarbeiten, dass eine Hörminderung des Trägers der Hörvorrichtung zumindest teilweise kompensiert wird. Insbesondere im Fall eines Hörhilfegeräts kann es sich bei dem Ausgabewandler neben einem Lautsprecher auch alternativ um einen sogenannten Knochenleitungshörer oder ein Cochlea-Implantat handeln, die zur mechanischen oder elektrischen Einkopplung des Tonsignals in das Gehör des Trägers eingerichtet sind. Unter dem Begriff Hörvorrichtungen fallen zusätzlich insbesondere auch Geräte wie z.B. sogenannte Tinnitus-Masker, Headsets, Kopfhörer und dergleichen.Hearing devices are usually used to output a sound signal to the hearing of the wearer of this hearing. The output is effected by means of an output transducer, usually acoustically via airborne sound by means of a loudspeaker (also referred to as "receiver" or "receiver"). Frequently, such hearing devices are used as so-called hearing aid devices (also short: hearing aids). For this purpose, the hearing devices normally comprise an acoustic input transducer (in particular a microphone) and a signal processor which is adapted to process the input signal (also: microphone signal) generated by the input transducer from the ambient sound using at least one custom-deposited signal processing algorithm such that a Hearing reduction of the wearer of the hearing device is at least partially compensated. In the case of a hearing aid in particular, the output transducer can also be, in addition to a loudspeaker, alternatively a so-called bone conduction earpiece or a cochlear implant, which are set up for the mechanical or electrical coupling of the sound signal into the hearing of the wearer. In addition, devices such as, for example, so-called tinnitus maskers, headsets, headphones and the like also fall in particular under the term hearing devices.
Moderne Hörvorrichtungen, insbesondere Hörhilfegeräte umfassen häufig einen sogenannten Klassifikator, der üblicherweise als Teil des Signalprozessors, der den oder den jeweiligen Signalverarbeitungsalgorithmus ausführt, ausgebildet ist. Bei einem solchen Klassifikator handelt es sich üblicherweise wiederum um einen Algorithmus, der dazu dient, anhand des mittels des Mikrophons erfassten Umgebungsschalls auf eine vorliegende Hörsituation zu schließen. Auf Basis der erkannten Hörsituation wird dann meist eine Anpassung des oder des jeweiligen Signalverarbeitungsalgorithmus an die charakteristischen Eigenschaften der vorliegenden Hörsituation vorgenommen. Insbesondere soll dadurch die Hörvorrichtung der Hörsituation entsprechend die für den Nutzer relevanten Informationen weitergeben. Zum Beispiels sind zur möglichst klaren Ausgabe von Musik andere Einstellungen (Parameterwerte unterschiedlicher Parameter) des oder eines der Signalverarbeitungsalgorithmen erforderlich, als zur verständlichen Ausgabe von Sprache bei lautem Umgebungsgeräusch. In Abhängigkeit von der erkannten Hörsituation werden die entsprechend zugeordneten Parameter dann verändert.Modern hearing devices, in particular hearing aids, often comprise a so-called classifier, which is usually designed as part of the signal processor which executes the respective signal processing algorithm or algorithms. Such a classifier is again usually an algorithm that serves to conclude an existing listening situation based on the ambient sound detected by means of the microphone. On the basis of the detected auditory situation, an adaptation of the or the respective signal processing algorithm to the characteristic properties of the present auditory situation is then usually carried out. In particular, the hearing device is thereby intended to pass on the information relevant for the user to the hearing situation. For example, for the clearest possible output of music, different settings (parameter values of different parameters) of the one or more of the signal processing algorithms are required than for intelligible speech output with loud ambient noise. Depending on the detected hearing situation, the correspondingly assigned parameters are then changed.
Übliche Hörsituationen sind z. B. Sprache in Ruhe, Sprache bei Störgeräuschen, Musik-Hören, (Fahren im) Fahrzeug. Zur Analyse des Umgebungsschalls (konkret des Mikrophonsignals) und zur Erkennung der jeweiligen Hörsituationen werden dabei zunächst aus dem Mikrophonsignal (oder einem daraus gebildeten Eingangssignal) verschiedene Merkmale (oft auch als "Features" bezeichnet) abgeleitet. Diese Merkmale werden dem Klassifikator zugeführt, der mit Hilfe von Analysemodellen wie z. B. einer sogenannten "Gauss'schen-Mischmoden-Analyse", einem "Hidden-Markov-Modell", einem neuronalen Netz oder dergleichen Wahrscheinlichkeiten für das Vorliegen bestimmter Hörsituationen ausgibt.Usual Hörsituationen are z. Eg speech at rest, speech at background noise, music listening, (driving in) vehicle. To analyze the ambient sound (specifically the microphone signal) and to recognize the respective listening situations, various features (often referred to as "features") are first derived from the microphone signal (or an input signal formed therefrom). These features are fed to the classifier, which is analyzed using analysis models such. As a so-called "Gaussian-mixed-mode analysis", a "Hidden Markov model", a neural network or the like probabilities for the presence of certain auditory situations outputs.
Häufig wird ein Klassifikator mittels Datenbanken, in denen für die jeweiligen Hörsituationen eine Vielzahl unterschiedlicher repräsentativer Hörproben abgelegt ist, auf die jeweilige Hörsituation "trainiert". Nachteilig hieran ist jedoch, dass in einer solchen Datenbank meist nicht alle im Alltag möglicherweise auftretenden Kombinationen von Geräuschen abgebildet sein können. Somit kann es bereits deshalb zu Fehlklassifikationen mancher Hörsituationen kommen.Frequently, a classifier is "trained" by means of databases in which a large number of different representative auditory samples are stored for the respective listening situations, to the respective hearing situation. The disadvantage of this, however, is that not all possibly occurring in everyday life combinations of sounds can be mapped in such a database usually. Thus, it may already come to misclassification of some Hörsituationen already.
Der Erfindung liegt die Aufgabe zugrunde, eine verbesserte Hörvorrichtung zu ermöglichen.The invention has for its object to provide an improved hearing.
Diese Aufgabe wird erfindungsgemäß gelöst durch ein Verfahren zum Betrieb einer Hörvorrichtung mit den Merkmalen des Anspruchs 1. Des Weiteren wird diese Aufgabe erfindungsgemäß gelöst durch eine Hörvorrichtung mit den Merkmalen des Anspruchs 14. Vorteilhafte und teils für sich erfinderische Ausführungsformen und Weiterentwicklungen der Erfindung sind in den Unteransprüchen der nachfolgenden Beschreibung dargelegt.This object is achieved by a method for operating a hearing with the features of
Das erfindungsgemäße Verfahren dient zum Betrieb einer Hörvorrichtung, die wenigstens ein Mikrophon zur Wandlung von Umgebungsschall in ein Mikrophonsignal umfasst. Verfahrensgemäß wird dabei aus dem Mikrophonsignal oder einem daraus gebildeten Eingangssignal eine Anzahl von Merkmalen (auch als "Features" bezeichnet) abgeleitet. Wenigstens drei Klassifikatoren, die unabhängig voneinander zur Analyse jeweils einer (vorzugsweise fest) zugeordneten akustischen Dimension implementiert sind, wird jeweils eine spezifisch zugeordnete Auswahl aus diesen Merkmalen zugeführt. Mittels des jeweiligen Klassifikators wird anschließend jeweils eine Information über eine Ausprägung der diesem Klassifikator zugeordneten akustischen Dimension generiert. In Abhängigkeit von mindestens einer der wenigstens drei Informationen über die jeweilige Ausprägung der zugeordneten akustischen Dimension wird dann wenigstens ein Signalverarbeitungsalgorithmus, der zur Verarbeitung des Mikrophonsignals bzw. des Eingangssignals in ein Ausgangssignal abgearbeitet (d. h. ausgeführt) wird, verändert.The method according to the invention serves to operate a hearing device which comprises at least one microphone for converting ambient sound into a microphone signal. According to the method, a number of features (also referred to as "features") are derived from the microphone signal or an input signal formed therefrom. At least three classifiers, which are implemented independently for the analysis of one (preferably fixed) associated acoustic dimension, are each supplied with a specifically assigned selection from these characteristics. By means of the respective classifier, information about an expression of the acoustic dimension assigned to this classifier is subsequently generated in each case. Depending on at least one of the at least three information about the respective characteristic of the assigned acoustic dimension, at least one signal processing algorithm which is processed (ie executed) for processing the microphone signal or the input signal is then modified.
Unter Veränderung des Signalverarbeitungsalgorithmus wird hier und im Folgenden insbesondere verstanden, dass wenigstens ein in dem Signalverarbeitungsalgorithmus enthaltener Parameter in Abhängigkeit von der Ausprägung der akustischen Dimension oder wenigstens einer der akustischen Dimensionen auf einen anderen Parameterwert gesetzt wird. Mit anderen Worten wird eine andere Einstellung des Signalverarbeitungsalgorithmus "angefahren" (d. h. bewirkt oder vorgenommen).A change in the signal processing algorithm is understood here and below as meaning in particular that at least one parameter contained in the signal processing algorithm is set to another parameter value as a function of the expression of the acoustic dimension or at least one of the acoustic dimensions. In other words, another setting of the signal processing algorithm is "approached" (ie, effected or made).
Unter dem Begriff "akustische Dimension" wird hier und im Folgenden insbesondere eine Gruppe von Hörsituationen verstanden, die aufgrund ihrer spezifischen Eigenschaften zusammenhängen. Vorzugsweise werden die in einer solchen akustischen Dimension abgebildeten Hörsituationen jeweils durch die gleichen Merkmale (Features) beschrieben und unterscheiden sich dabei insbesondere aufgrund des aktuellen Werts der jeweiligen Merkmale.The term "acoustic dimension" is understood here and below to mean, in particular, a group of listening situations which are related on the basis of their specific properties. Preferably, the listening situations depicted in such an acoustic dimension are each described by the same features (features) and in this case differ, in particular, on the basis of the current value of the respective features.
Unter dem Begriff "Ausprägung" der jeweiligen akustischen Dimension wird hier und im Folgenden insbesondere verstanden, ob (im Sinne einer binären Unterscheidung) oder (in bevorzugter Variante) zu welchem Grad (beispielsweise zu welchem Prozentsatz) die oder die jeweilige in der jeweiligen akustischen Dimension abgebildete Hörsituation vorliegt. Ein solcher Grad bzw. Prozentsatz stellt dabei vorzugsweise einen Wahrscheinlichkeitswert für das Vorliegen der jeweiligen Hörsituation dar. Beispielsweise können hierbei in einer auf das Vorhandensein von Sprache gerichteten akustischen Dimension die Hörsituationen "Sprache in Ruhe", "Sprache im Störgeräusch" oder (insbesondere nur) "Störgeräusch" (d. h. es liegt keine Sprache vor) abgebildet sein, wobei die Information über die Ausprägung vorzugsweise wiederum jeweils Prozentangaben enthält (bspw. 30 % Wahrscheinlichkeit für Sprache im Störgeräusch und 70 % Wahrscheinlichkeit für nur Störgeräusch).The term "expression" of the respective acoustic dimension is understood here and below in particular as meaning (in the sense of a binary distinction) or (in a preferred variant) to what degree (for example to what percentage) the respective one or more in the respective acoustic dimension shown hearing situation is present. Such a degree or percentage preferably represents a probability value for the presence of the respective hearing situation. For example, in an acoustic dimension directed to the presence of speech, the listening situations "speech at rest", "speech in noise" or (especially only) "Noise" (ie, there is no language) be mapped, the information about the expression preferably again in each case percentages include (eg 30% probability of speech in noise and 70% probability of only noise).
Die erfindungsgemäße Hörvorrichtung umfasst wie vorstehend beschrieben wenigstens das eine Mikrophon zur Wandlung des Umgebungsschalls in das Mikrophonsignal sowie einen Signalprozessor, in dem wenigstens die drei vorstehend beschriebenen Klassifikatoren unabhängig voneinander zur Analyse der jeweils (vorzugsweise fest) zugeordneten akustischen Dimension implementiert sind. Der Signalprozessor ist dabei dazu eingerichtet, das erfindungsgemäße Verfahren vorzugsweise selbsttätig durchzuführen. Mit anderen Worten ist der Signalprozessor dazu eingerichtet, aus dem Mikrophonsignal oder dem daraus gebildeten Eingangssignal die Anzahl von Merkmalen abzuleiten, den drei Klassifikatoren jeweils eine spezifisch zugeordnete Auswahl aus den Merkmalen zuzuführen, mit Hilfe des jeweiligen Klassifikators eine Information über die Ausprägung der jeweils zugeordneten akustischen Dimension zu generieren und in der Abhängigkeit von mindestens einer der drei Informationen wenigstens einen (vorzugsweise der akustischen Dimension entsprechend zugeordneten) Signalverarbeitungsalgorithmus zu verändern und vorzugsweise auf das Mikrophonsignal bzw. das Eingangssignal anzuwenden.The hearing device according to the invention comprises, as described above, at least one microphone for converting the ambient sound into the microphone signal and a signal processor in which at least the three classifiers described above are implemented independently of one another for the analysis of the respective (preferably fixed) associated acoustic dimension. The signal processor is set up to perform the inventive method preferably automatically. In other words, the signal processor is set up to derive the number of features from the microphone signal or the input signal formed therefrom, to supply each of the three classifiers with a specifically assigned selection from the features, with the aid of the respective classifier information about the characteristics of the respective associated ones To generate acoustic dimension and depending on at least one of the three information at least one (preferably corresponding to the acoustic dimension assigned) signal processing algorithm to change and preferably apply to the microphone signal or the input signal.
In bevorzugter Ausgestaltung ist der Signalprozessor (auch als Signalverarbeitungseinheit bezeichnet) zumindest im Kern durch einen Mikrocontroller mit einem Prozessor und einem Datenspeicher gebildet, in dem die Funktionalität zur Durchführung des erfindungsgemäßen Verfahrens in Form einer Betriebssoftware ("Firmware") programmtechnisch implementiert ist, so dass das Verfahren - gegebenenfalls in Interaktion mit einem Nutzer der Hörvorrichtung - bei Ausführung der Betriebssoftware in dem Mikrocontroller automatisch durchgeführt wird. Alternativ ist der Signalprozessor durch ein nicht-programmierbares elektronisches Bauteil, z.B. einen ASIC, gebildet, in dem die Funktionalität zur Durchführung des erfindungsgemäßen Verfahrens mit schaltungstechnischen Mitteln implementiert ist.In a preferred embodiment, the signal processor (also referred to as signal processing unit) is formed at least in the core by a microcontroller with a processor and a data memory in which the functionality for performing the method according to the invention in the form of operating software ("firmware") is implemented by programming, so that the method - optionally in interaction with a user of the hearing device - is automatically performed in the execution of the operating software in the microcontroller. Alternatively, the signal processor is constituted by a non-programmable electronic component, e.g. an ASIC, in which the functionality for carrying out the method according to the invention is implemented by means of circuitry.
Dadurch, dass erfindungsgemäß mindestens drei Klassifikatoren zur Analyse jeweils einer zugeordneten akustischen Dimension und somit insbesondere zur Erkennung jeweils einer Hörsituation eingerichtet und vorgesehen sind, wird vorteilhafterweise ermöglicht, dass zumindest drei Hörsituationen unabhängig voneinander erkannt werden können. Dadurch wird die Flexibilität der Hörvorrichtung im Erkennen von Hörsituationen vorteilhaft erhöht. Die Erfindung geht dabei von der Erkenntnis aus, dass zumindest manche Hörsituationen auch vollständig unabhängig (d. h. sich insbesondere nicht oder lediglich in einem unerheblichen Maß gegenseitig beeinflussend) voneinander und parallel zueinander vorliegen können. Mittels des erfindungsgemäßen Verfahrens sowie mittels der erfindungsgemäßen Hörvorrichtung kann somit das Risiko vermindert werden, dass es zumindest hinsichtlich der wenigstens drei mittels des jeweils zugeordneten Klassifikators analysierten akustischen Dimension zu sich gegenseitig ausschließenden und insbesondere widersprüchlichen Klassifikationen (d. h. Einschätzung der aktuell vorliegenden akustischen Situation) kommt. Insbesondere können auf einfache Weise (vollständig) parallel vorliegende Hörsituationen erkannt und in der Veränderung des Signalverarbeitungsalgorithmus berücksichtigt werden.Because according to the invention at least three classifiers are set up and provided for analysis in each case of an assigned acoustic dimension and thus in particular for the detection of a respective hearing situation, it is advantageously made possible that at least three hearing situations can be recognized independently of each other. As a result, the flexibility of the hearing device in detecting hearing situations is advantageously increased. The invention is based on the recognition that at least some listening situations may also be completely independent of one another (ie in particular not influencing each other or only to a negligible extent) from one another and parallel to one another. Thus, by means of the method according to the invention and by means of the hearing device according to the invention, the risk can be reduced that mutually exclusive and, in particular, contradictory classifications (ie assessment of the currently present acoustic situation) occur, at least with regard to the at least three acoustic dimensions analyzed by the respective assigned classifier. In particular, simple can Ways (completely) present in parallel present hearing situations and be taken into account in the change of the signal processing algorithm.
Der erfindungsgemäßen Hörvorrichtung kommen dabei die gleichen Vorteile zu wie dem erfindungsgemäßen Verfahren zum Betrieb der Hörvorrichtung.The hearing device according to the invention has the same advantages as the method according to the invention for operating the hearing device.
In einer bevorzugten Verfahrensvariante werden mehrere, d. h. wenigstens zwei oder mehr Signalverarbeitungsalgorithmen insbesondere parallel zur Verarbeitung des Mikrophonsignals bzw. des Eingangssignals herangezogen. Die Signalverarbeitungsalgorithmen "arbeiten" dabei vorzugsweise auf (wenigstens) jeweils einer zugeordneten akustischen Dimension, d. h. die Signalverarbeitungsalgorithmen dienen zur Verarbeitung (bspw. Filterung, Verstärkung, Dämpfung) von Signalanteilen, die für die in der jeweils zugeordneten akustischen Dimension enthaltenen oder abgebildeten Hörsituationen relevant sind. Zur Anpassung der Signalverarbeitung in Abhängigkeit von der Ausprägung der jeweiligen akustischen Dimension umfassen die Signalverarbeitungsalgorithmen wenigstens einen, vorzugsweise mehrere Parameter, die in ihren Parameterwerten verändert werden können. Vorzugsweise können die Parameterwerte dabei in Abhängigkeit von der jeweiligen Wahrscheinlichkeit der Ausprägung auch in mehreren Abstufungen (graduell oder kontinuierlich) verändert werden. Dadurch wird eine besonders flexible und vorteilhafterweise an eine Vielzahl von graduellen Unterschieden zwischen mehreren Hörsituationen anpassbare Signalverarbeitung ermöglicht.In a preferred variant of the method, several, i. H. at least two or more signal processing algorithms used in particular in parallel to the processing of the microphone signal or the input signal. The signal processing algorithms preferably "work" on (at least) one respective associated acoustic dimension, ie. H. the signal processing algorithms are used to process (eg filtering, amplifying, attenuating) signal components that are relevant to the listening situations contained or reproduced in the respectively assigned acoustic dimension. To adapt the signal processing as a function of the expression of the respective acoustic dimension, the signal processing algorithms comprise at least one, preferably a plurality of parameters which can be changed in their parameter values. Preferably, the parameter values can also be changed in several gradations (gradual or continuous) depending on the respective probability of the characteristic. This allows a particularly flexible and advantageously to a variety of gradual differences between multiple listening situations customizable signal processing.
In einer zweckmäßigen Verfahrensvariante wird mindestens zwei der mindestens drei Klassifikatoren jeweils eine unterschiedliche Auswahl aus den Merkmalen zugeführt. Darunter wird hier und im Folgenden insbesondere verstanden, dass für den jeweiligen Klassifikator eine unterschiedliche Anzahl und/oder unterschiedliche Merkmale ausgewählt und diesem zugeführt werden.In a suitable method variant, at least two of the at least three classifiers are each supplied with a different selection from the characteristics. This is understood here and below as meaning in particular that a different number and / or different features are selected and supplied to the respective classifier.
Die Konjunktion "und/oder" ist hier und im Folgenden derart zu verstehen, dass die mittels dieser Konjunktion verknüpften Merkmale sowohl gemeinsam als auch als Alternativen zueinander ausgebildet sein können.The conjunction "and / or" is to be understood here and below in such a way that the features linked by means of this conjunction can be designed both jointly and as alternatives to one another.
In einer weiteren zweckmäßigen Verfahrensvariante werden jedem der Klassifikatoren mit der entsprechend zugeordneten Auswahl insbesondere nur für die Analyse der zugeordneten akustischen Dimension relevante Merkmale zugeführt. Mit anderen Worten werden für jeden Klassifikator vorzugsweise nur die Merkmale ausgewählt und zugeführt, die zur Bestimmung der in der jeweiligen akustischen Dimension abgebildeten Hörsituation auch tatsächlich erforderlich sind. Dadurch kann bei der Analyse der jeweiligen akustischen Dimension vorteilhafterweise Rechenaufwand sowie Aufwand bei der Implementierung des jeweiligen Klassifikators eingespart werden, da für die jeweilige akustische Dimension unerhebliche Merkmale von vornherein unberücksichtigt bleiben. Vorteilhafterweise kann hierdurch auch das Risiko einer Fehlklassifikation aufgrund einer irrtümlichen Berücksichtigung nicht relevanter Merkmale weiter verringert werden.In a further expedient method variant, each of the classifiers with the correspondingly assigned selection is supplied with features relevant only to the analysis of the assigned acoustic dimension. In other words, for each classifier, preferably only those features are selected and supplied which are actually required for determining the auditory situation depicted in the respective acoustic dimension. As a result, in the analysis of the respective acoustic dimension, it is advantageously possible to save on computational effort and expenditure in the implementation of the respective classifier, since characteristics inconsequential for the respective acoustic dimension are disregarded from the outset. Advantageously, the risk of misclassification due to an erroneous consideration of non-relevant features can be further reduced thereby.
In einer vorteilhaften Verfahrensvariante wird, insbesondere für den Fall, dass in jedem Klassifikator nur die jeweils relevanten Merkmale herangezogen werden, für jeden der Klassifikatoren ein spezifischer Analysealgorithmus zur Auswertung der (jeweils spezifisch) zugeführten Merkmale herangezogen. Auch hierdurch lässt sich wiederum vorteilhafterweise Rechenaufwand einsparen. Des Weiteren können vergleichsweise komplizierte Algorithmen oder Analysemodelle wie z. B. Gauss'sche Mischmoden, neuronale Netze oder Hidden-Markov-Modelle, die insbesondere zur Analyse einer Vielzahl von verschiedenen, voneinander unabhängigen Merkmalen herangezogen werden, entfallen. Vielmehr ist insbesondere jeder der Klassifikatoren somit auf ein konkretes "Problem", d. h. hinsichtlich seines Analysealgorithmus auf die diesem Klassifikator konkret zugeordnete akustische Dimension "zugeschnitten" (d. h. angepasst oder ausgelegt). Die vorstehend beschriebenen, vergleichsweise komplexen Analysemodelle können im Rahmen der Erfindung dennoch für spezifische akustische Dimensionen zum Einsatz kommen, wobei auch hierbei aufgrund der Ausrichtung des entsprechenden Klassifikators auf eine oder wenige von der spezifischen akustischen Dimension umfassten Hörsituationen Aufwand bei der Implementierung eines solchen vergleichsweise aufwendigen Modells eingespart werden kann.In an advantageous variant of the method, in particular for the case that only the respective relevant features are used in each classifier, a specific analysis algorithm for evaluating the (respectively specific) supplied features is used for each of the classifiers. This, in turn, can advantageously also save computational effort. Furthermore, comparatively complicated algorithms or analysis models such. As Gaussian mixed modes, neural networks or hidden Markov models, which are used in particular for the analysis of a variety of different, independent characteristics eliminated. Rather, in particular each of the classifiers is thus "tailored" (ie adapted or designed) to a concrete "problem", ie with regard to its analysis algorithm, to the acoustic dimension concretely assigned to this classifier. The comparatively complex analysis models described above can nevertheless be used for specific acoustic dimensions in the context of the invention, whereby in this case, due to the orientation of the corresponding classifier to one or a few auditory situations encompassed by the specific acoustic dimension, effort is required to implement such a comparatively complex model can be saved.
In einer bevorzugten Verfahrensvariante werden als die wenigstens drei akustischen Dimensionen insbesondere die Dimensionen "Fahrzeug", "Musik" und "Sprache" herangezogen. Insbesondere wird innerhalb der jeweiligen akustischen Dimension somit ermittelt, ob der Nutzer der Hörvorrichtung sich in einem Fahrzeug befindet, konkret mit diesem Fahrzeug fährt, Musik hört bzw. ob Sprache vorliegt. In letzterem Fall wird vorzugsweise im Rahmen dieser akustischen Dimension ermittelt, ob Sprache in Ruhe, Sprache im Störgeräusch oder keine Sprache und dabei vorzugsweise nur Störgeräusch vorliegt. Bei diesen drei akustischen Dimensionen handelt es sich insbesondere um die Dimensionen, die im Alltag eines Nutzers der Hörvorrichtung üblicherweise besonders häufig auftreten und dabei auch unabhängig voneinander sind. In einer optionalen Weiterbildung dieser Verfahrensvariante wird ein vierter Klassifikator zur Analyse einer vierten akustischen Dimension herangezogen, bei der es sich insbesondere um die Lautheit (auch: "Lautstärke") von Umgebungsgeräuschen (auch als "Störgeräusche" bezeichnet) handelt. Die Ausprägungen dieser akustischen Dimension erstrecken sich dabei vorzugsweise graduell oder kontinuierlich über mehrere Zwischenstufen von sehr leise bis sehr laut. Die Informationen zu den Ausprägungen insbesondere der akustischen Dimensionen Fahrzeug und Musik können im Gegensatz dazu optional "binär" sein, d. h. es wird nur erkannt, ob Fahren im Fahrzeug vorliegt oder nicht, bzw. ob Musik gehört wird oder nicht. Vorzugsweise liegen aber alle Informationen der anderen drei akustischen Dimensionen als eine Art Wahrscheinlichkeitswert kontinuierlich vor. Dies ist insbesondere vorteilhaft, da Fehler bei der Analyse der jeweiligen akustischen Dimension nicht ausgeschlossen werden können, sowie da dadurch auch im Gegensatz zu binären Informationen auf einfache Weise "weichere" Übergänge zwischen verschiedenen Einstellungen bewirkt werden können.In a preferred variant of the method, in particular the dimensions "vehicle", "music" and "language" are used as the at least three acoustic dimensions. In particular, it is thus determined within the respective acoustic dimension whether the user of the hearing device is in a vehicle, driving specifically with this vehicle, listening to music or if speech is present. In the latter case, it is preferably determined within the scope of this acoustic dimension whether speech is available in silence, speech in noise or no speech and preferably only noise. These three acoustic dimensions are, in particular, the dimensions that usually occur particularly frequently in the everyday life of a user of the hearing device and are also independent of each other. In an optional development of this method variant, a fourth classifier is used to analyze a fourth acoustic dimension, which is in particular the loudness (also: "loudness") of ambient noise (also referred to as "noise"). The characteristics of this acoustic dimension preferably extend gradually or continuously over a plurality of intermediate stages from very quiet to very loud. The information on the characteristics, in particular of the acoustic dimensions vehicle and music, in contrast, can optionally be "binary", i. H. it is only recognized whether driving in the vehicle is present or not, or whether music is heard or not. Preferably, however, all the information of the other three acoustic dimensions is present as a kind of probability value continuously. This is particularly advantageous because errors in the analysis of the respective acoustic dimension can not be excluded, and as a result, in contrast to binary information, "softer" transitions between different settings can be effected in a simple manner.
In zusätzlichen oder optional alternativen Weiterbildungen werden jeweils weitere Klassifikatoren zur Wind- und/oder Nachhallschätzung sowie zur Detektion der eigenen Stimme des Trägers der Hörvorrichtung herangezogen.In additional or optionally alternative developments, in each case further classifiers for wind and / or reverberation estimation as well as for the detection of one's own voice of the wearer of the hearing device are used.
In einer zweckmäßigen Verfahrensvariante werden aus dem Mikrophonsignal bzw. dem Eingangssignal Merkmale abgeleitet, die aus einer (insbesondere nichtabschließenden) Gruppe ausgewählt sind, die insbesondere die Merkmale Signalpegel, 4-Hz-Einhüllenden-Modulation, Onset-Gehalt, Pegel eines Hintergrundgeräuschs (auch als "Noise Floor Level" bezeichnet, optional bei einer vorgegebenen Frequenz), spektraler Schwerpunkt des Hintergrundgeräuschs, Stationarität (insbesondere bei einer vorgegebenen Frequenz), Tonalität und Windaktivität umfasst.In an expedient variant of the method, features are derived from the microphone signal or the input signal which originate from a (in particular non-terminating) In particular, the following are selected: signal level, 4 Hz envelope modulation, onset content, background noise level (also referred to as noise floor level, optionally at a given frequency), spectral centroid of the background noise, stationarity (in particular at a given frequency), tonality and wind activity.
In einer weiteren zweckmäßigen Verfahrensvariante werden der akustischen Dimension Fahrzeug zumindest die Merkmale Pegel des Hintergrundgeräuschs, spektraler Schwerpunkt des Hintergrundgeräuschs und Stationarität (sowie optional auch das Merkmal der Windaktivität) zugeordnet. Der akustischen Dimension Musik werden vorzugsweise die Merkmale Onset-Gehalt, Tonalität und Pegel des Hintergrundgeräuschs zugeordnet. Der akustischen Dimension Sprache werden insbesondere die Merkmale Onset-Gehalt und 4-Hz-Einhüllenden-Modulation zugeordnet. Der gegebenenfalls vorhandenen Dimension Lautheit des Umgebungsgeräuschs werden insbesondere die Merkmale Pegel des Hintergrundgeräuschs, Signalpegel und spektraler Schwerpunkt des Hintergrundgeräuschs zugeordnet.In a further expedient variant of the method, the acoustic dimension vehicle is assigned at least the characteristics level of the background noise, spectral center of gravity of the background noise and stationarity (and optionally also the characteristic of the wind activity). The acoustic dimension music is preferably assigned the characteristics onset content, tonality and level of the background noise. In particular, the characteristics of onset content and 4 Hz envelope modulation are assigned to the acoustic dimension speech. The possibly existing dimension loudness of the ambient noise is assigned in particular the characteristics level of the background noise, signal level and spectral center of gravity of the background noise.
In einer weiteren zweckmäßigen Verfahrensvariante wird für jeden Klassifikator eine spezifisch zugeordnete zeitliche Stabilisierung berücksichtigt. Insbesondere wird hierbei bei manchen der Klassifikatoren vorzugsweise bei bereits in der Vergangenheit (bspw. in einem vorangegangenem Zeitabschnitt von vorgegebener Dauer) erkanntem Vorliegen einer Hörsituation (d. h. insbesondere bei einer bestimmten Ausprägung der akustischen Dimension) angenommen, dass dieser Zustand (die Ausprägung) dann auch mit hoher Wahrscheinlichkeit zum aktuellen Zeitpunkt noch vorliegt. Beispielsweise wird hierzu ein gleitender Mittelwert über (insbesondere eine vorgegebene Anzahl von) vorangegangenen Zeitabschnitten gebildet. Alternativ kann auch eine Art "Totzeitglied" vorgesehen werden, mittels dessen in einem nachfolgenden Zeitabschnitt die Wahrscheinlichkeit erhöht wird, dass die im vorangegangenen Zeitabschnitt vorliegende Ausprägung immer noch vorliegt. Beispielsweise wird angenommen, wenn Fahren im Fahrzeug in den vorausgegangenen fünf Minuten erkannt wurde, dass diese Situation weiterhin vorliegt. Vorzugsweise für die Dimensionen Fahrzeug und Musik werden vergleichsweise "starke" Stabilisierungen herangezogen, d. h. es werden nur vergleichsweise langsame oder seltene Veränderungen der entsprechend zugeordneten Hörsituationen angenommen. Für die Dimension Sprache wird hingegen zweckmäßigerweise keine oder nur eine "schwache" Stabilisierung vorgenommen, da hier schnelle und/oder häufige Veränderungen der Hörsituationen angenommen werden. Sprachsituationen können oft nur wenige Sekunden (bspw. etwa 5 Sekunden) oder wenige Minuten andauern, wohingegen Fahren im Fahrzeug meist für mehrere Minuten (bspw. mehr als 3 bis 30 Minuten oder sogar Stunden) vorliegt. Eine weitere optionale Variante zur Stabilisierung kann auch über ein Zählprinzip erfolgen, bei dem bei einer vergleichsweise schnellen (bspw. 100 Millisekunden bis wenige Sekunden) Detektionstaktung ein Zähler ("counter") inkrementiert wird und erst bei Überschreiten eines Grenzwerts für diesen Zähler die "Erkennung" der jeweiligen Hörsituation ausgelöst wird. Dies ist bspw. als Kurzzeitstabilisierung bei einem gemeinsamen Klassifikator für "alle" Hörsituationen zweckmäßig. Als Abwandlung zur Stabilisierung im vorliegenden Fall ist es dabei bspw. denkbar, jeder Hörsituation einen eigenen Grenzwert zuzuweisen und diesen insbesondere für die Hörsituation "Fahren im Fahrzeug" und/oder "Musik-Hören" herabzusetzen, wenn bereits für eine vorgegebene vorausgehende Zeitspanne die jeweilige Hörsituation erkannt wurde.In a further expedient method variant, a specifically assigned temporal stabilization is taken into account for each classifier. In particular, in the case of some of the classifiers, in the case of a hearing situation (ie, in particular in the case of a specific expression of the acoustic dimension) already recognized in the past (for example in a preceding period of a predetermined duration), it is then assumed that this condition (the expression) is also present with high probability at the current time is still present. For example, for this purpose a moving average is formed over (in particular a predefined number of) preceding time segments. Alternatively, it is also possible to provide a type of "dead-time element" by means of which the probability is increased in a subsequent period of time that the characteristic present in the preceding time period is still present. For example, assuming that driving in the vehicle has been detected in the previous five minutes, it is assumed that this situation is still present. Preferably for the dimensions vehicle and music are comparatively "strong" stabilizations are used, ie only comparatively slow or rare changes in the correspondingly assigned listening situations are assumed. For the dimension language, on the other hand, expediently no or only a "weak" stabilization is undertaken, since here rapid and / or frequent changes of the listening situations are assumed. Voice situations can often last only a few seconds (for example about 5 seconds) or a few minutes, whereas driving in the vehicle usually lasts for several minutes (for example more than 3 to 30 minutes or even hours). A further optional variant for stabilization can also take place via a counting principle in which a counter ("counter") is incremented at a comparatively fast (for example 100 milliseconds to a few seconds) detection cycle and only when a limit value for this counter is exceeded the "Detection "of the respective hearing situation is triggered. This is expedient, for example, as short-term stabilization in the case of a common classifier for "all" listening situations. As a modification to the stabilization in the present case, it is conceivable, for example, to assign each hearing situation its own limit value and to reduce this in particular for the listening situation "driving in the vehicle" and / or "listening to music", if already for a given preceding time period the respective one Hearing situation was detected.
In einer weiteren zweckmäßigen Verfahrensvariante wird der oder der jeweilige Signalverarbeitungsalgorithmus in Abhängigkeit von mindestens zwei der wenigstens drei Informationen über die Ausprägung der jeweils zugeordneten akustischen Dimension angepasst. In zumindest einem Signalverarbeitungsalgorithmus werden also die Informationen mehrerer Klassifikatoren berücksichtigt.In a further expedient variant of the method, the respective signal processing algorithm is adapted as a function of at least two of the at least three information about the expression of the respective associated acoustic dimension. In at least one signal processing algorithm, therefore, the information of several classifiers is taken into account.
In einer zweckmäßigen Verfahrensvariante werden die jeweiligen Informationen der einzelnen Klassifikatoren insbesondere zunächst einem Fusionsglied zu einer gemeinsamen Auswertung zugeführt ("fusioniert"). Anhand dieser gemeinsamen Auswertung aller Informationen wird insbesondere eine Gesamtinformation über die vorliegenden Hörsituationen erstellt. Vorzugsweise wird dabei eine dominante Hörsituation ermittelt - insbesondere anhand des die Wahrscheinlichkeit wiedergebenden Grads der Ausprägung. Der oder der jeweilige Signalverarbeitungsalgorithmus wird dabei an diese dominante Hörsituation angepasst. Optional erfolgt hierbei eine Priorisierung einer Hörsituation (nämlich er dominanten), indem der oder der jeweilige Signalverarbeitungsalgorithmus nur in Abhängigkeit von der dominanten Hörsituation verändert wird, während andere Signalverarbeitungsalgorithmen und/oder die von anderen Hörsituationen abhängigen Parameter unverändert bleiben oder auf einen Parameterwert, der keinen Einfluss auf die Signalverarbeitung hat, gesetzt werden.In an expedient variant of the method, the respective information of the individual classifiers is in particular first supplied to a fusion member for a common evaluation ("merged"). On the basis of this joint evaluation of all information in particular a total information about the present hearing situations is created. In this case, a dominant hearing situation is preferably determined - in particular on the basis of the degree of expressiveness representing the probability. The or the respective signal processing algorithm is adapted to this dominant listening situation. Optionally, a prioritization of a hearing situation (namely, the dominant one) takes place in that the or the respective signal processing algorithm is changed only as a function of the dominant hearing situation, while other signal processing algorithms and / or the parameters dependent on other hearing situations remain unchanged or a parameter value which does not Has an influence on the signal processing.
In einer Weiterbildung der vorstehend beschriebenen Verfahrensvariante wird anhand der gemeinsamen Auswertung aller Informationen insbesondere eine als Subsituation bezeichnete Hörsituation ermittelt, die gegenüber der dominanten Hörsituation eine geringere Dominanz aufweist. Diese oder die jeweilige Subsituation wird dabei zusätzlich bei der vorgenannten Anpassung des oder des jeweiligen Signalverarbeitungsalgorithmus an die dominante Hörsituation und/oder zur Anpassung eines spezifisch der akustischen Dimension dieser Subsituation zugeordneten Signalverarbeitungsalgorithmus berücksichtigt. Insbesondere führt hierbei diese Subsituation zu einer im Vergleich zu der dominanten Hörsituation geringeren Veränderung des oder des jeweils zugeordneten Parameters. Für den Fall, dass beispielsweise als dominante Hörsituation Sprache im Störgeräusch ermittelt und als Subsituation Musik werden, wird daraufhin ein zur möglichst klaren Sprachverständlichkeit bei Störgeräusch dienender Signalverarbeitungsalgorithmus in einem oder mehreren Parametern vergleichsweise stark verändert, um eine möglichst hohe Sprachverständlichkeit zu erreichen. Da aber auch Musik vorliegt, werden Parameter, die zur Dämpfung von Umgebungsgeräuschen dienen, weniger stark eingestellt (als wenn nur ein Störgeräusch vorliegt), um die Töne der Musik nicht völlig abzudämpfen. Ein (insbesondere zusätzlicher) zur klaren Klangwiedergabe von Musik dienender Signalverarbeitungsalgorithmus wird dabei außerdem weniger stark eingestellt als bei Musik als dominanter Hörsituation (aber stärker als bei keiner Musik), um die Sprachanteile nicht zu überdecken. Somit kann, insbesondere aufgrund der voneinander unabhängigen Detektion von unterschiedlichen Hörsituationen sowie aufgrund der dadurch ermöglichten feineren Anpassung der Signalverarbeitungsalgorithmen eine besonders präzise Anpassung der Signalverarbeitung der Hörvorrichtung an die tatsächlich vorliegende Hörsituation erfolgen.In a development of the method variant described above, based on the common evaluation of all information, in particular a hearing situation designated as a sub-situation is determined, which has a lower dominance than the dominant hearing situation. This or the respective sub-situation is additionally taken into account in the above-mentioned adaptation of the or the respective signal processing algorithm to the dominant hearing situation and / or adaptation of a signal processing algorithm specifically assigned to the acoustic dimension of this sub-situation. In particular, this sub-situation leads to a smaller change of the respectively assigned parameter compared to the dominant hearing situation. In the event, for example, that speech is determined as the dominant hearing situation and becomes a subsonic music, a signal processing algorithm serving as clear as possible in the case of noise is then comparatively strongly modified in one or more parameters in order to achieve as high a speech intelligibility as possible. However, as music is present, parameters that attenuate ambient noise are set less (as if there is only a noise) so as not to completely dampen the sounds of the music. In addition, a (especially additional) signal processing algorithm for clear sound reproduction of music is set less strongly than in music as the dominant listening situation (but stronger than in any music) in order not to mask the speech components. Thus, in particular due to the independent detection of different listening situations and due to the finer adjustment of the signal processing algorithms thereby made possible a particularly precise adaptation the signal processing of the hearing to the actual present hearing situation.
Wie bereits vorstehend beschrieben wird vorzugsweise in wenigstens einem der gegebenenfalls mehreren Signalverarbeitungsalgorithmen das parallele Vorliegen mehrerer Hörsituationen berücksichtigt.As already described above, the parallel existence of a plurality of hearing situations is preferably taken into account in at least one of the possibly multiple signal processing algorithms.
In einer alternativen Verfahrensvariante wird der oder vorzugsweise jeder Signalverarbeitungsalgorithmus wenigstens einem der Klassifikatoren zugeordnet. In diesem Fall wird vorzugsweise wenigstens ein Parameter eines jeden Signalverarbeitungsalgorithmus (insbesondere unmittelbar) in Abhängigkeit von der von dem jeweiligen Klassifikator ausgegebenen Information über die Ausprägung der zugeordneten akustischen Dimension verändert. Vorzugsweise ist dieser Parameter bzw. dessen Parameterwert als eine Funktion der jeweiligen Information ausgebildet. Somit wird die Information über die Ausprägung der jeweiligen akustischen Dimension insbesondere direkt für eine Anpassung der Signalverarbeitung genutzt. Mit anderen Worten "steuert" jeder Klassifikator wenigstens einen Parameter wenigstens eines Signalverarbeitungsalgorithmus. Eine gemeinsame Auswertung aller Informationen kann hierbei ausbleiben. Insbesondere werden in diesem Fall besonders viele Informationen über die Verteilung der voneinander unabhängigen Hörsituationen im aktuell vorliegenden, vom Umgebungsschalls beschriebenen "Bild" berücksichtigt, so dass wiederum eine besonders feine Anpassung der Signalverarbeitung gefördert wird. Insbesondere können hierbei auch vollständig parallele Hörsituationen - bspw. 100 % Sprache im Störgeräusch bei 100 % Fahren im Fahrzeug, oder 100 % Musik bei 100 % Fahren im Fahrzeug - auf einfache Weise und mit geringem Informationsverlust berücksichtigt werden.In an alternative method variant, the or preferably each signal processing algorithm is assigned to at least one of the classifiers. In this case, preferably at least one parameter of each signal processing algorithm (in particular directly) is changed as a function of the information output by the respective classifier about the characteristic of the assigned acoustic dimension. Preferably, this parameter or its parameter value is designed as a function of the respective information. Thus, the information about the expression of the respective acoustic dimension is used in particular directly for an adaptation of the signal processing. In other words, each classifier "controls" at least one parameter of at least one signal processing algorithm. A common evaluation of all information can be omitted here. In particular, in this case, a great deal of information about the distribution of the independent listening situations in the currently available "picture" described by the ambient sound is taken into account, so that again a particularly fine adaptation of the signal processing is promoted. In particular, even completely parallel listening situations - for example 100% speech in noise at 100% driving in the vehicle, or 100% music at 100% driving in the vehicle - can be considered in a simple manner and with little loss of information.
In einer weiteren zweckmäßigen Verfahrensvariante wird wenigstens einem der Klassifikatoren eine Zustandsinformation zugeführt, die unabhängig von dem Mikrophonsignal oder dem Eingangssignal erzeugt wird. Diese Zustandsinformation wird dabei insbesondere zusätzlich zur Auswertung der jeweiligen akustischen Dimension berücksichtigt. Beispielsweise handelt es sich dabei um eine Bewegungs- und/oder Ortsinformation die beispielsweise zur Auswertung der akustischen Dimension Fahrzeug herangezogen wird. Diese Bewegungs- und/oder Ortsinformation wird beispielsweise mit einem in der Hörvorrichtung selbst oder in einem signalübertragungstechnisch mit dieser verbundenen System (bspw. einem Smartphone) angeordneten Beschleunigungs- oder (globalen) Positionssensor erzeugt. Beispielsweise lässt sich dabei anhand einer vorliegenden (einen vorgegebenen Wert aufweisenden) Bewegungsgeschwindigkeit bei der Auswertung der akustischen Dimension Fahrzeug die Wahrscheinlichkeit für das Vorliegen der Hörsituation Fahren im Fahrzeug auf einfache Weise zusätzlich zu der akustischen Auswertung erhöhen. Man spricht hier auch von "Augmentierung" eines Klassifikators.In a further expedient variant of the method, state information is fed to at least one of the classifiers and is generated independently of the microphone signal or the input signal. This state information is taken into account in particular in addition to the evaluation of the respective acoustic dimension. For example, this is a movement and / or location information, for example, for the evaluation of the acoustic Dimension vehicle is used. This movement and / or location information is generated, for example, with an acceleration or (global) position sensor arranged in the hearing device itself or in a signal transmission technology connected to it (eg, a smartphone). For example, the probability of the presence of the hearing situation driving in the vehicle can be increased in a simple manner in addition to the acoustic evaluation on the basis of a present (having a predetermined value) movement speed in the evaluation of the acoustic dimension vehicle. This is also called "augmentation" of a classifier.
Nachfolgend werden Ausführungsbeispiele der Erfindung anhand einer Zeichnung näher erläutert. Darin zeigen:
- Fig. 1
- in einer schematischen Übersichtsdarstellung eine Hörvorrichtung,
- Fig. 2
- in einem schematischen Blockschaltbild einen Signallaufplan der Hörvorrichtung gemäß
Fig. 1 , - Fig. 3
- in einem schematischen Ablaufplan ein Verfahren zum Betrieb der Hörvorrichtung gemäß
Fig. 1 , und - Fig. 4
- in Ansicht gemäß
Fig. 2 ein alternatives Ausführungsbeispiel des Signallaufplans.
- Fig. 1
- in a schematic overview of a hearing device,
- Fig. 2
- in a schematic block diagram of a signal processing plan of the hearing device according to
Fig. 1 . - Fig. 3
- in a schematic flowchart, a method for operating the hearing according to
Fig. 1 , and - Fig. 4
- in view according to
Fig. 2 an alternative embodiment of the signal processing plan.
Einander entsprechende Teile und Größen sind in allen Figuren stets mit gleichen Bezugszeichen versehen.Corresponding parts and sizes are always provided with the same reference numerals in all figures.
In
Zur Erkennung unterschiedlicher Hörsituationen und zur darauffolgenden Anpassung der Signalverarbeitung ist das Hörgerät 1, konkret dessen Signalprozessor 4, dazu eingerichtet, ein im Folgenden anhand von
Konkret werden, wie aus
In einem alternativen Ausführungsbeispiel wird lediglich "binär" ermittelt, ob Sprache, ggf. im Störgeräusch oder nur Störgeräusch, bzw. ob Musik oder Fahren im Fahrzeug vorliegt oder nicht.In an alternative embodiment, only "binary" is determined whether speech, possibly in noise or only noise, or whether music or driving in the vehicle is present or not.
Die jeweilige Ausprägung der akustischen Dimensionen wird in einem Verfahrensschritt 50 an ein Fusionsmodul 60 ausgegeben (siehe
Der Klassifikator KF umfasst dabei in nicht näher dargestellter Art und Weise eine zeitliche Stabilisierung. Diese ist insbesondere darauf ausgerichtet, dass eine Fahrt im Fahrzeug üblicherweise längere Zeit andauert, und somit für den Fall, dass bereits in vorausgegangenen Zeitabschnitten, von beispielsweise jeweils 30 Sekunden bis zu fünf Minuten Dauer, Fahren im Fahrzeug erkannt wurde und unter der Annahme, dass die Situation Fahren im Fahrzeug immer noch andauert die Wahrscheinlichkeit für das Vorliegen dieser Hörsituation bereits vorab erhöht ist. Entsprechendes ist auch in dem Klassifikator KM eingerichtet und vorgesehen.The classifier K F includes in a manner not shown a temporal stabilization. This is particularly geared to the fact that a ride in the vehicle usually lasts longer time, and thus in the event that already in previous periods of, for example, each 30 seconds to five minutes duration, driving in the vehicle was detected and assuming that the situation driving in the vehicle still lasts the probability for the existence of this hearing situation is already increased in advance. The same is also set up and provided in the classifier K M.
In einem alternativen Ausführungsbeispiel gemäß
Der Gegenstand der Erfindung ist nicht auf die vorstehend beschriebenen Ausführungsbeispiele beschränkt. Vielmehr können weitere Ausführungsformen der Erfindung von dem Fachmann aus der vorstehenden Beschreibung abgeleitet werden. Insbesondere können die anhand der verschiedenen Ausführungsbeispiele beschriebenen Einzelmerkmale der Erfindung und deren Ausgestaltungsvarianten auch in anderer Weise miteinander kombiniert werden. So kann bspw. das Hörgerät 1 anstelle des dargestellten hinter-dem-Ohr-Hörgeräts auch als in-dem-Ohr-Hörgerät ausgebildet sein.The object of the invention is not limited to the embodiments described above. Rather, other embodiments of the invention may be derived by those skilled in the art from the foregoing description. In particular, the individual features of the invention described with reference to the various exemplary embodiments and their design variants can also be combined with one another in a different manner. For example, instead of the illustrated behind-the-ear hearing device, the
- 11
- Hörgeräthearing Aid
- 22
- Gehäusecasing
- 33
- Mikrophonmicrophone
- 44
- Signalprozessorsignal processor
- 55
- Lautsprecherspeaker
- 66
- Batteriebattery
- 77
- Schallschlauchsound tube
- 88th
- Ohrstückearpiece
- 1010
- MerkmalsanalysemodulFeature analysis module
- 2020
- Verfahrensschrittstep
- 3030
- Verfahrensschrittstep
- 4040
- Verfahrensschrittstep
- 5050
- Verfahrensschrittstep
- 6060
- Fusionsmodulfusion module
- A1-A4 A 1 -A 4
- SignalverarbeitungsalgorithmusSignal processing algorithm
- KS, KM, KF K S , K M , K F
- Klassifikatorclassifier
- ME, MO, MT, MP, MW, MZ, MM M E , M O , M T , M P , M W , M Z , M M
- Merkmalfeature
- SA S A
- Ausgangssignaloutput
- SE S E
- Eingangssignalinput
- SM S M
- Mikrophonsignalmicrophone signal
Claims (14)
wobei mindestens zwei der wenigstens drei Klassifikatoren (KS, KM, KF) jeweils eine unterschiedliche Auswahl aus den Merkmalen (ME, MO, MT, MP, MW, MZ, MM) zugeführt wird.Method according to claim 1,
wherein at least two of the at least three classifiers (K S , K M , K F ) in each case a different selection from the features (M E , M O , M T , M P , M W , M Z , M M ) is supplied.
wobei jedem der Klassifikatoren (KS, KM, KF) mit der entsprechend zugeordneten Auswahl nur für die Analyse der jeweils zugeordneten akustischen Dimension relevante Merkmale (ME, MO, MT, MP, MW, MZ, MM) zugeführt werden.Method according to claim 1 or 2,
wherein each of the classifiers (K S , K M , K F ) with the correspondingly assigned selection only for the analysis of the respectively associated acoustic dimension relevant features (M E , M O , M T , M P , M W , M Z , M M ) are supplied.
wobei für jeden der Klassifikatoren (KS, KM, KF) ein spezifischer Analysealgorithmus zur Auswertung der jeweiligen zugeführten Merkmale (ME, MO, MT, MP, MW, MZ, MM) herangezogen wird.Method according to one of claims 1 to 3,
wherein for each of the classifiers (K S , K M , K F ), a specific analysis algorithm for evaluating the respective supplied features (M E , M O , M T , M P , M W , M Z , M M ) is used.
wobei als die wenigstens drei akustischen Dimensionen Fahrzeug, Musik und Sprache herangezogen werden.Method according to one of claims 1 to 4,
wherein the vehicle, music and speech are used as the at least three acoustic dimensions.
wobei aus dem Mikrophonsignal (SM) bzw. dem Eingangssignal (SE) Merkmale ausgewählt aus Signalpegel, 4-Hertz-Einhüllenden-Modulation (ME), Onset-Gehalt (MO), Pegel eines Hintergrundgeräuschs (MP), spektraler Schwerpunkt des Hintergrundgeräuschs (MZ), Stationarität (MM), Tonalität (MT), Windaktivität (MW) abgeleitet werden.Method according to one of claims 1 to 5,
wherein from the microphone signal (S M ) and the input signal (S E ) features selected from signal level, 4-hertz envelope modulation (M E ), onset content (M O ), level of background noise (M P ), spectral Focus of the background noise (M Z ), stationarity (M M ), tonality (M T ), wind activity (M W ) are derived.
wobei der akustischen Dimension Fahrzeug zumindest die Merkmale Pegel des Hintergrundgeräuschs (MP), spektraler Schwerpunkt des Hintergrundgeräuschs (MZ) und Stationarität (MM) zugeordnet werden, wobei der akustischen Dimension Musik die Merkmale Onset-Gehalt (MO), Tonalität (MT) und Pegel des Hintergrundgeräuschs (MP) zugeordnet werden, und wobei der akustischen Dimension Sprache die Merkmale Onset-Gehalt (MO) und 4-Hertz-Einhüllenden-Modulation (ME) zugeordnet werden.Method according to one of claims 5 and 6,
wherein the acoustic dimension vehicle, at least the characteristics of level of the background noise (M P), spectral center of gravity of the background noise (M Z) and stationarity (M M) are assigned, wherein the acoustic dimension music features Onset content (M O), tonality ( M T ) and levels of background noise (M P ), and wherein the acoustic dimension speech is assigned the characteristics onset-content (M O ) and 4-Hertz-envelope-modulation (M E ).
wobei für jeden Klassifikator (KS, KM, KF) eine spezifisch zugeordnete zeitliche Stabilisierung berücksichtigt wird.Method according to one of claims 1 to 7,
wherein for each classifier (K S , K M , K F ) a specifically associated temporal stabilization is taken into account.
wobei der oder der jeweilige Signalverarbeitungsalgorithmus (A1, A2, A3, A4) in Abhängigkeit von mindestens zwei der wenigstens drei Informationen über die Ausprägung der jeweils zugeordneten akustischen Dimension verändert wird.Method according to one of claims 1 to 8,
wherein the or the respective signal processing algorithm (A 1 , A 2 , A 3 , A 4 ) in dependence on at least two of the at least three information about the expression of the respectively assigned acoustic dimension is changed.
wobei die Informationen der jeweiligen Klassifikatoren (KS, KM, KF) einer gemeinsamen Auswertung zugeführt werden, wobei aufgrund dieser gemeinsamen Auswertung eine dominante Hörsituation ermittelt wird, und wobei der oder der jeweilige Signalverarbeitungsalgorithmus (A1, A2, A3, A4) an diese dominante Hörsituation angepasst wird.Method according to one of claims 1 to 9,
wherein the information of the respective classifiers (K S , K M , K F ) are supplied to a common evaluation, a dominant hearing situation being determined on the basis of this joint evaluation, and the respective signal processing algorithm (A 1 , A 2 , A 3 , A 4 ) is adapted to this dominant hearing situation.
wobei wenigstens eine Subsituation mit gegenüber der dominanten Hörsituation geringerer Dominanz ermittelt wird, und wobei diese oder die jeweilige Subsituation bei der Veränderung des Signalverarbeitungsalgorithmus (A1, A2, A3, A4) oder wenigstens eines der Signalverarbeitungsalgorithmen (A1, A2, A3, A4) berücksichtigt wird.Method according to claim 10,
wherein at least one sub-situation with respect to the dominant hearing situation of lesser dominance is determined, and wherein these or the respective sub-situation in the change of the signal processing algorithm (A 1 , A 2 , A 3 , A 4 ) or at least one of the signal processing algorithms (A 1 , A 2 , A 3 , A 4 ) is taken into account.
wobei jeder Signalverarbeitungsalgorithmus (A1, A2, A3, A4) wenigstens einem der Klassifikatoren (KS, KM, KF) zugeordnet ist, und wobei wenigstens ein Parameter eines jeden Signalverarbeitungsalgorithmus (A1, A2, A3, A4) in Abhängigkeit von der von dem zugeordneten Klassifikator (KS, KM, KF) ausgegebenen Information über die Ausprägung der entsprechenden akustischen Dimension verändert wird.Method according to one of claims 1 to 8,
wherein each signal processing algorithm (A 1 , A 2 , A 3 , A 4 ) is associated with at least one of the classifiers (K S , K M , K F ), and wherein at least one parameter of each signal processing algorithm (A 1 , A 2 , A 3 , A 4 ) is changed in dependence on the output from the associated classifier (K S , K M , K F ) information about the expression of the corresponding acoustic dimension.
wobei wenigstens einem der Klassifikatoren (KS, KM, KF) eine unabhängig von dem Mikrophonsignal (SM) oder dem Eingangssignal (SE) erzeugte Zustandsinformation zugeführt, die zusätzlich zur Auswertung der jeweiligen akustischen Dimension berücksichtigt wird.Method according to one of claims 1 to 12,
wherein at least one of the classifiers (K S , K M , K F ) supplied independently of the microphone signal (S M ) or the input signal (S E ) state information is taken into account in addition to the evaluation of the respective acoustic dimension.
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
DE102017205652.5A DE102017205652B3 (en) | 2017-04-03 | 2017-04-03 | Method for operating a hearing device and hearing device |
Publications (2)
Publication Number | Publication Date |
---|---|
EP3386215A1 true EP3386215A1 (en) | 2018-10-10 |
EP3386215B1 EP3386215B1 (en) | 2021-11-17 |
Family
ID=61231167
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
EP18157220.7A Active EP3386215B1 (en) | 2017-04-03 | 2018-02-16 | Hearing aid and method for operating a hearing aid |
Country Status (5)
Country | Link |
---|---|
US (1) | US10462584B2 (en) |
EP (1) | EP3386215B1 (en) |
CN (1) | CN108696813B (en) |
DE (1) | DE102017205652B3 (en) |
DK (1) | DK3386215T3 (en) |
Families Citing this family (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE102019203786A1 (en) * | 2019-03-20 | 2020-02-13 | Sivantos Pte. Ltd. | Hearing aid system |
DE102019218808B3 (en) * | 2019-12-03 | 2021-03-11 | Sivantos Pte. Ltd. | Method for training a hearing situation classifier for a hearing aid |
DE102020208720B4 (en) * | 2019-12-06 | 2023-10-05 | Sivantos Pte. Ltd. | Method for operating a hearing system depending on the environment |
DE102019220408A1 (en) * | 2019-12-20 | 2021-06-24 | Sivantos Pte. Ltd. | Procedure for fitting a hearing instrument and associated hearing system |
DE102022212035A1 (en) | 2022-11-14 | 2024-05-16 | Sivantos Pte. Ltd. | Method for operating a hearing aid and hearing aid |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20030144838A1 (en) * | 2002-01-28 | 2003-07-31 | Silvia Allegro | Method for identifying a momentary acoustic scene, use of the method and hearing device |
EP1858291A1 (en) * | 2006-05-16 | 2007-11-21 | Phonak AG | Hearing system and method for deriving information on an acoustic scene |
WO2008084116A2 (en) * | 2008-03-27 | 2008-07-17 | Phonak Ag | Method for operating a hearing device |
EP2670168A1 (en) * | 2012-06-01 | 2013-12-04 | Starkey Laboratories, Inc. | Adaptive hearing assistance device using plural environment detection and classification |
DE102014207311A1 (en) * | 2014-04-16 | 2015-03-05 | Siemens Medical Instruments Pte. Ltd. | Automatic selection of listening situations |
Family Cites Families (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1160450A (en) * | 1994-09-07 | 1997-09-24 | 摩托罗拉公司 | System for recognizing spoken sounds from continuous speech and method of using same |
WO2001076321A1 (en) | 2000-04-04 | 2001-10-11 | Gn Resound A/S | A hearing prosthesis with automatic classification of the listening environment |
EP1513371B1 (en) * | 2004-10-19 | 2012-08-15 | Phonak Ag | Method for operating a hearing device as well as a hearing device |
US8249284B2 (en) * | 2006-05-16 | 2012-08-21 | Phonak Ag | Hearing system and method for deriving information on an acoustic scene |
DK2064918T3 (en) * | 2006-09-05 | 2015-01-26 | Gn Resound As | A hearing-aid with histogram based lydmiljøklassifikation |
WO2008028484A1 (en) * | 2006-09-05 | 2008-03-13 | Gn Resound A/S | A hearing aid with histogram based sound environment classification |
US20100002782A1 (en) * | 2008-07-02 | 2010-01-07 | Yutaka Asanuma | Radio communication system and radio communication method |
WO2013110348A1 (en) | 2012-01-27 | 2013-08-01 | Siemens Medical Instruments Pte. Ltd. | Adaptation of a classification of an audio signal in a hearing aid |
WO2015024585A1 (en) * | 2013-08-20 | 2015-02-26 | Widex A/S | Hearing aid having an adaptive classifier |
WO2017059881A1 (en) * | 2015-10-05 | 2017-04-13 | Widex A/S | Hearing aid system and a method of operating a hearing aid system |
JP6402810B1 (en) * | 2016-07-22 | 2018-10-10 | 株式会社リコー | Three-dimensional modeling resin powder, three-dimensional model manufacturing apparatus, and three-dimensional model manufacturing method |
-
2017
- 2017-04-03 DE DE102017205652.5A patent/DE102017205652B3/en not_active Expired - Fee Related
-
2018
- 2018-02-16 DK DK18157220.7T patent/DK3386215T3/en active
- 2018-02-16 EP EP18157220.7A patent/EP3386215B1/en active Active
- 2018-03-30 US US15/941,106 patent/US10462584B2/en active Active
- 2018-04-03 CN CN201810287586.2A patent/CN108696813B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20030144838A1 (en) * | 2002-01-28 | 2003-07-31 | Silvia Allegro | Method for identifying a momentary acoustic scene, use of the method and hearing device |
EP1858291A1 (en) * | 2006-05-16 | 2007-11-21 | Phonak AG | Hearing system and method for deriving information on an acoustic scene |
WO2008084116A2 (en) * | 2008-03-27 | 2008-07-17 | Phonak Ag | Method for operating a hearing device |
EP2670168A1 (en) * | 2012-06-01 | 2013-12-04 | Starkey Laboratories, Inc. | Adaptive hearing assistance device using plural environment detection and classification |
DE102014207311A1 (en) * | 2014-04-16 | 2015-03-05 | Siemens Medical Instruments Pte. Ltd. | Automatic selection of listening situations |
Also Published As
Publication number | Publication date |
---|---|
CN108696813A (en) | 2018-10-23 |
DK3386215T3 (en) | 2022-02-07 |
US20180288534A1 (en) | 2018-10-04 |
CN108696813B (en) | 2021-02-19 |
EP3386215B1 (en) | 2021-11-17 |
DE102017205652B3 (en) | 2018-06-14 |
US10462584B2 (en) | 2019-10-29 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
DE102017205652B3 (en) | Method for operating a hearing device and hearing device | |
EP1379102B1 (en) | Sound localization in binaural hearing aids | |
DE102005032274B4 (en) | Hearing apparatus and corresponding method for eigenvoice detection | |
EP3451705B1 (en) | Method and apparatus for the rapid detection of own voice | |
EP2603018B1 (en) | Hearing aid with speaking activity recognition and method for operating a hearing aid | |
DE102019206743A1 (en) | Hearing aid system and method for processing audio signals | |
EP3427498B1 (en) | Method for operating a hearing device and apparatus for own voice detection based on an individual threshold | |
EP3873108A1 (en) | Hearing system with at least one hearing instrument worn in or on the ear of the user and method for operating such a hearing system | |
EP3840418A1 (en) | Method for adjusting a hearing aid and corresponding hearing system | |
EP3396978B1 (en) | Hearing aid and method for operating a hearing aid | |
EP3836139A1 (en) | Hearing aid and method for coupling two hearing aids together | |
EP2114089A1 (en) | Method and device for calculating the extent of wear on hearing aids | |
EP2239963B1 (en) | Method and hearing device for adjusting a hearing aid to recorded data in an external unit | |
EP3926981B1 (en) | Hearing system with at least one hearing instrument worn in or on the ear of the user and method for operating such a hearing system | |
DE102006001730A1 (en) | Sound system, method for improving the voice quality and / or intelligibility of voice announcements and computer program | |
DE102008046040A1 (en) | Method for operating a hearing device with directivity and associated hearing device | |
EP3793218A1 (en) | Hearing device and method for operating a hearing device | |
EP1926087A1 (en) | Adjustment of a hearing device to a speech signal | |
DE102016207936A1 (en) | Method for operating a hearing device | |
EP2658289B1 (en) | Method for controlling an alignment characteristic and hearing aid | |
EP1881738A2 (en) | Method of operating a hearing aid and assembly with a hearing aid | |
DE102010041435A1 (en) | Method for reconstructing a speech signal and hearing device | |
EP2262282A2 (en) | Method for determining a frequency response and corresponding hearing aid | |
EP1348315B1 (en) | Method for use of a hearing-aid and corresponding hearing aid | |
EP2635048A2 (en) | Amplification of a speech signal based on the input level |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PUAI | Public reference made under article 153(3) epc to a published international application that has entered the european phase |
Free format text: ORIGINAL CODE: 0009012 |
|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: THE APPLICATION HAS BEEN PUBLISHED |
|
AK | Designated contracting states |
Kind code of ref document: A1 Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR |
|
AX | Request for extension of the european patent |
Extension state: BA ME |
|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: REQUEST FOR EXAMINATION WAS MADE |
|
17P | Request for examination filed |
Effective date: 20190409 |
|
RBV | Designated contracting states (corrected) |
Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR |
|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: EXAMINATION IS IN PROGRESS |
|
17Q | First examination report despatched |
Effective date: 20191014 |
|
GRAP | Despatch of communication of intention to grant a patent |
Free format text: ORIGINAL CODE: EPIDOSNIGR1 |
|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: GRANT OF PATENT IS INTENDED |
|
INTG | Intention to grant announced |
Effective date: 20200225 |
|
RIN1 | Information on inventor provided before grant (corrected) |
Inventor name: AUBREVILLE, MARC Inventor name: LUGGER, MARKO |
|
GRAJ | Information related to disapproval of communication of intention to grant by the applicant or resumption of examination proceedings by the epo deleted |
Free format text: ORIGINAL CODE: EPIDOSDIGR1 |
|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: EXAMINATION IS IN PROGRESS |
|
INTC | Intention to grant announced (deleted) | ||
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: EXAMINATION IS IN PROGRESS |
|
GRAP | Despatch of communication of intention to grant a patent |
Free format text: ORIGINAL CODE: EPIDOSNIGR1 |
|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: GRANT OF PATENT IS INTENDED |
|
INTG | Intention to grant announced |
Effective date: 20210407 |
|
GRAJ | Information related to disapproval of communication of intention to grant by the applicant or resumption of examination proceedings by the epo deleted |
Free format text: ORIGINAL CODE: EPIDOSDIGR1 |
|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: EXAMINATION IS IN PROGRESS |
|
REG | Reference to a national code |
Ref country code: DE Ref legal event code: R079 Ref document number: 502018007846 Country of ref document: DE Free format text: PREVIOUS MAIN CLASS: H04R0025000000 Ipc: G10L0025810000 |
|
GRAP | Despatch of communication of intention to grant a patent |
Free format text: ORIGINAL CODE: EPIDOSNIGR1 |
|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: GRANT OF PATENT IS INTENDED |
|
INTC | Intention to grant announced (deleted) | ||
RIN1 | Information on inventor provided before grant (corrected) |
Inventor name: AUBREVILLE, MARC Inventor name: LUGGER, MARKO |
|
RIC1 | Information provided on ipc code assigned before grant |
Ipc: G10L 25/81 20130101AFI20210610BHEP Ipc: H04R 25/00 20060101ALI20210610BHEP Ipc: G10L 25/84 20130101ALI20210610BHEP |
|
INTG | Intention to grant announced |
Effective date: 20210629 |
|
GRAS | Grant fee paid |
Free format text: ORIGINAL CODE: EPIDOSNIGR3 |
|
GRAA | (expected) grant |
Free format text: ORIGINAL CODE: 0009210 |
|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: THE PATENT HAS BEEN GRANTED |
|
AK | Designated contracting states |
Kind code of ref document: B1 Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR |
|
REG | Reference to a national code |
Ref country code: GB Ref legal event code: FG4D Free format text: NOT ENGLISH |
|
REG | Reference to a national code |
Ref country code: DE Ref legal event code: R096 Ref document number: 502018007846 Country of ref document: DE |
|
REG | Reference to a national code |
Ref country code: IE Ref legal event code: FG4D Free format text: LANGUAGE OF EP DOCUMENT: GERMAN |
|
REG | Reference to a national code |
Ref country code: AT Ref legal event code: REF Ref document number: 1448738 Country of ref document: AT Kind code of ref document: T Effective date: 20211215 |
|
REG | Reference to a national code |
Ref country code: DK Ref legal event code: T3 Effective date: 20220201 |
|
REG | Reference to a national code |
Ref country code: LT Ref legal event code: MG9D |
|
REG | Reference to a national code |
Ref country code: NL Ref legal event code: MP Effective date: 20211117 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: RS Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20211117 Ref country code: LT Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20211117 Ref country code: FI Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20211117 Ref country code: BG Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20220217 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: IS Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20220317 Ref country code: SE Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20211117 Ref country code: PT Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20220317 Ref country code: PL Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20211117 Ref country code: NO Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20220217 Ref country code: NL Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20211117 Ref country code: LV Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20211117 Ref country code: HR Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20211117 Ref country code: GR Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20220218 Ref country code: ES Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20211117 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: SM Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20211117 Ref country code: SK Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20211117 Ref country code: RO Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20211117 Ref country code: EE Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20211117 Ref country code: CZ Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20211117 |
|
REG | Reference to a national code |
Ref country code: DE Ref legal event code: R097 Ref document number: 502018007846 Country of ref document: DE |
|
PLBE | No opposition filed within time limit |
Free format text: ORIGINAL CODE: 0009261 |
|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: NO OPPOSITION FILED WITHIN TIME LIMIT |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: MC Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20211117 |
|
REG | Reference to a national code |
Ref country code: BE Ref legal event code: MM Effective date: 20220228 |
|
26N | No opposition filed |
Effective date: 20220818 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: LU Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20220216 Ref country code: AL Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20211117 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: SI Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20211117 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: IE Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20220216 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: BE Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20220228 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: IT Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20211117 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: HU Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT; INVALID AB INITIO Effective date: 20180216 |
|
REG | Reference to a national code |
Ref country code: AT Ref legal event code: MM01 Ref document number: 1448738 Country of ref document: AT Kind code of ref document: T Effective date: 20230216 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: AT Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20230216 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: MK Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20211117 Ref country code: CY Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20211117 Ref country code: AT Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20230216 |
|
PGFP | Annual fee paid to national office [announced via postgrant information from national office to epo] |
Ref country code: DE Payment date: 20240216 Year of fee payment: 7 Ref country code: CH Payment date: 20240301 Year of fee payment: 7 Ref country code: GB Payment date: 20240222 Year of fee payment: 7 |
|
PGFP | Annual fee paid to national office [announced via postgrant information from national office to epo] |
Ref country code: FR Payment date: 20240222 Year of fee payment: 7 Ref country code: DK Payment date: 20240221 Year of fee payment: 7 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: TR Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20211117 |